Metraipolis › archive › dc_1defc144ca74

On the Chain-of-Thought Monitorability of Looped Language Models — arXiv:2610.02741

Source
arXiv
Original
https://arxiv.org/abs/2610.02741
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:12.061Z
SHA-256 of the archived text
dc7374c981e2634fbdd7d2d7c0ce847fb64885c34581c9afde1f8e1d50f9be4a
Stable URL of this page
https://metraipolis.com/documento/dc_1defc144ca74

How to cite

On the Chain-of-Thought Monitorability of Looped Language Models — arXiv:2610.02741 — arXiv, https://arxiv.org/abs/2610.02741 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1defc144ca74 (Metraipolis archive dc_1defc144ca74, sha256 dc7374c981e2634fbdd7d2d7c0ce847fb64885c34581c9afde1f8e1d50f9be4a)
BibTeX
@misc{dc1defc144ca74,
  title = {On the Chain-of-Thought Monitorability of Looped Language Models — arXiv:2610.02741},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02741},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1defc144ca74; sha256 dc7374c981e2634fbdd7d2d7c0ce847fb64885c34581c9afde1f8e1d50f9be4a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02741. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Chain-of-thought (CoT) monitoring provides a promising approach for detecting undesirable model behavior. Looped language models (LoopLMs) repeatedly apply shared transformer layers, increasing effective computational depth and enabling additional latent computation without increasing model size. However, the effect of looped architectures on CoT monitorability remains largely unexplored. In this work, we provide the first systematic evaluation of CoT monitorability in LoopLMs. We study two complementary settings: (1) varying the loop depth within the same LoopLM family to isolate the effect of additional recurrent computation, and (2) comparing LoopLMs with non-looped language models matched by parameter size, transformer-layer count, or effective depth to study whether LoopLMs are less monitorable. Across eight tasks from MonitorBench and both standard and stress-test settings, we observe task-dependent reductions in CoT monitorability under stress tests on specific Logic/Science/Engineering \texttt{Cue Answer} tasks, while other tasks exhibit weaker or qualitatively different trends. Our diagnosis suggests that these declines are not fully explained by task difficulty, verification pass rate, or generated token length; qualitative examples further suggest changes in how deeper-loop models explicitly use or attribute provided cues. Our cross-model comparison finds no evidence that LoopLMs are systematically less monitorable than non-looped language models matched on size or depth. Overall, our results suggest that deeper loop depth can reduce CoT monitorability in some tasks under stress tests, but looped transformer architecture alone does not necessarily imply lower monitorability.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02741 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T22:45:55.623Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).